Skill · Second-model review
Sol loop
Has one OpenAI GPT Sol reviewer check your diff, three rounds by default, with a ledger of findings and a brief against scope creep. It stops when both agree or the budget ends.
- Author
- Theo Browne (community)
- Source
- t3dotgg/tstack at version
11e37a7 - Licence
- MIT
- Needs
- Needs an account or credits: Access to OpenAI's GPT Sol model (paid); A harness that can run it as a subagent, such as T3 Code
- Works in
- Terminal agents such as Claude Code, Codex and Cursor
- Reviewed
- Nov 2026, skill file read in full
- Note
- Needs a route to GPT Sol and reports a blocker if there is none; it does not substitute another model. When it pushes to a pull request it adds a line that names the reviewing model.
Install only this skill
npx skills add t3dotgg/tstack@11e37a74d0a6868c121cd0910ab2b3bd9873b92a --skill sol-loop -g -y
Comes in these collections
Browne